© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3621
    Prev
    Next
    INDEX
    Explanations

    occurances of "else" in source code, but also picks up "skill", "Skill" and "catch" by mistake

    oai_token-act-pair · gemini-2.0-flash

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     whoſe
    -0.85
     houſe
    -0.84
     beſt
    -0.84
     purpoſe
    -0.82
     itſelf
    -0.82
     himſelf
    -0.81
     raiſ
    -0.80
     uſ
    -0.79
     theſe
    -0.78
     againſt
    -0.77
    POSITIVE LOGITS
    ngrx
    0.73
    IsContent
    0.71
     wireType
    0.71
    WriteBarrier
    0.68
     iprot
    0.66
     ProtoMessage
    0.66
    Hochspringen
    0.66
     Mam
    0.65
    AndEndTag
    0.65
    Билгалдахарш
    0.64
    Activations Density 0.236%

    No Known Activations