© 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. 9760
    Prev
    Next
    INDEX
    Explanations

    incoherent text with multiple quotes and mentions of cold.

    oai_token-act-pair · gemini-2.0-flash

    words related to unexpected emotional expressions

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

    Disjointed text snippets

    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
    /*
    -0.80
     its
    -0.51
    帖最后由
    -0.50
    ci
    -0.49
    KommentareTeilen
    -0.48
    gle
    -0.46
    ellemző
    -0.46
     createSlice
    -0.45
     ar
    -0.44
    人的
    -0.44
    POSITIVE LOGITS
     Efq
    0.76
    ſelf
    0.72
    DotNetBar
    0.71
    Formazione
    0.70
     raiſ
    0.69
     purpoſe
    0.68
    ^(@)
    0.68
    $.
    0.66
    )];
    0.65
     faſt
    0.65
    Activations Density 1.330%

    No Known Activations