© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    mentions of names, particularly in lists, and cartoon references.

    oai_token-act-pair · gemini-2.0-flash

    names of characters and objects

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

    fictional stories and characters

    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
     itſelf
    -0.75
     neceff
    -0.68
    IBOutlet
    -0.67
     themſelves
    -0.66
    @[+][
    -0.66
    ]--;
    -0.65
     considérons
    -0.63
    ArrowToggle
    -0.63
     يتيمه
    -0.63
     occaf
    -0.62
    POSITIVE LOGITS
    lasi
    0.48
     Per
    0.47
     toto
    0.45
     Po
    0.44
     Italijanski
    0.42
    <<
    0.42
     rada
    0.42
     S
    0.42
    endregion
    0.41
    Per
    0.41
    Activations Density 0.772%

    No Known Activations