© 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. 12459
    Prev
    Next
    INDEX
    Explanations

    the word "damage" and sometimes other words near "damage" or related to negative experiences

    oai_token-act-pair · gemini-2.0-flash

    damage

    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
     itſelf
    -1.92
     doubtnut
    -1.83
     Efq
    -1.77
     myſelf
    -1.77
     Majefty
    -1.65
     Monfieur
    -1.61
     raiſ
    -1.61
     ―――――
    -1.59
     pleaſure
    -1.59
     ſind
    -1.56
    POSITIVE LOGITS
     "
    1.30
     
    1.17
     '
    1.14
     S
    1.02
     N
    1.02
     $
    0.95
     B
    0.93
     P
    0.92
     “
    0.92
     D
    0.92
    Activations Density 4.109%

    No Known Activations