© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7565
    Prev
    Next
    INDEX
    Explanations

    negative sentiments around crime in a city

    oai_token-act-pair · gemini-2.0-flash

    technical terms and coding related concepts

    np_token-act-pair-logits · gpt-4o-mini

    legal and crime contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.53
     scoperta
    -0.52
    Bless
    -0.49
     Sergi
    -0.49
     دیکھیے
    -0.48
    Jeografia
    -0.48
     CreateTagHelper
    -0.48
    appartamento
    -0.48
    Ena
    -0.47
    localctx
    -0.47
    POSITIVE LOGITS
     MessageBoxIcon
    0.55
     ContentValues
    0.53
     FetchType
    0.51
    smithy
    0.49
     FixedUpdate
    0.48
    ʊ
    0.48
     TextInputType
    0.48
    Facades
    0.48
    KommentareTeilen
    0.47
    MethodManager
    0.47
    Activations Density 0.691%

    No Known Activations