© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    tools or actions that can cause injury or harm

    oai_token-act-pair · gemini-2.0-flash

    sharp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     sharp
    -2.03
    sharp
    -1.85
     Sharp
    -1.77
    Sharp
    -1.67
     sharper
    -1.63
     SHARP
    -1.61
     sharpness
    -1.40
     sharpen
    -1.37
    shar
    -1.30
     sharpened
    -1.22
    POSITIVE LOGITS
    ⓧ
    0.63
    WebServlet
    0.50
    tagHelperRunner
    0.49
    ccm
    0.47
    SequentialGroup
    0.47
    iNdEx
    0.47
    ]),
    0.46
     Melville
    0.45
     Herzegovina
    0.44
     تانيه
    0.44
    Activations Density 5.254%

    No Known Activations