© 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. 10523
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "can't", "won't", or "haven't".

    oai_token-act-pair · gemini-2.0-flash

    t

    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
    stylesheet
    -0.65
     marinho
    -0.60
    ="@+
    -0.59
     FontWeight
    -0.59
    UIAlert
    -0.57
     myſelf
    -0.56
     itſelf
    -0.56
     alſo
    -0.55
    +#+#
    -0.55
    enumi
    -0.54
    POSITIVE LOGITS
     cant
    1.20
     cannot
    1.16
     Cannot
    1.11
     CANT
    1.02
    cannot
    1.02
    Cant
    1.02
    cant
    0.97
     Cant
    0.93
     couldn
    0.91
    Cannot
    0.90
    Activations Density 2.089%

    No Known Activations