© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 13694
    Prev
    Next
    INDEX
    Explanations

    words (and short phrases) indicating that there is a problem with a game, or in a more general sense, some other problem that must be dealt with.

    oai_token-act-pair · gemini-2.0-flash

    but/and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    my
    -0.47
    AxisAlignment
    -0.44
     "
    -0.43
    2
    -0.40
    ⓧ
    -0.39
    CppMethod
    -0.38
     my
    -0.37
     pán
    -0.37
    1
    -0.37
     -
    -0.36
    POSITIVE LOGITS
    ſelf
    0.95
     myſelf
    0.89
     himſelf
    0.84
     Majefty
    0.83
    ſelves
    0.82
     itſelf
    0.79
     Theſe
    0.79
     Diſ
    0.78
     Efq
    0.78
     Chriftian
    0.77
    Activations Density 3.235%

    No Known Activations