© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    words and suffixes that end with the letters "me", "ne", "te", "ing" or "l"

    oai_token-act-pair · gemini-2.0-flash

    terms related to memory and presence

    np_token-act-pair-logits · gpt-4o-mini
    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
    出版年
    -0.86
    OGND
    -0.71
    localctx
    -0.71
    
    -0.70
     ModelExpression
    -0.69
    mybatisplus
    -0.68
     Audiodateien
    -0.66
    ніципалі
    -0.65
    AndroidJUnit
    -0.65
    SourceChecksum
    -0.64
    POSITIVE LOGITS
    hmer
    0.49
    Non
    0.44
    tt
    0.44
    N
    0.42
    AtIndexPath
    0.42
    lobo
    0.42
    われました
    0.41
    uro
    0.41
    agle
    0.41
    usc
    0.40
    Activations Density 1.312%

    No Known Activations