© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    words related to needing something done or being able to do something

    oai_token-act-pair · gemini-2.0-flash

    words related to removal or disconnection

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

    removal

    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
    MergeFrom
    -0.58
     HasFactory
    -0.57
     AssemblyTitle
    -0.57
     gynnwys
    -0.56
    saraba
    -0.56
    سطس
    -0.55
    IContainer
    -0.53
     ExecuteAsync
    -0.53
    RuleContext
    -0.51
    swamp
    -0.51
    POSITIVE LOGITS
     removal
    1.40
     remove
    1.36
     removed
    1.33
     Remove
    1.30
     off
    1.28
     removing
    1.26
     Removal
    1.23
     removes
    1.17
    Remove
    1.16
     REMOV
    1.16
    Activations Density 1.946%

    No Known Activations