© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15966
    Prev
    Next
    INDEX
    Explanations

    angle brackets with forward slashes in them, often found in closing HTML or XML tags

    oai_token-act-pair · gemini-2.0-flash

    "/>"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    "/>
    -0.98
    '/>
    -0.86
    "/>
    -0.72
    glEnd
    -0.71
    }}/>
    -0.63
    =""/>
    -0.63
    "/></
    -0.62
     Roskov
    -0.61
    }/>
    -0.61
    abestanden
    -0.60
    POSITIVE LOGITS
    éez
    0.45
    funny
    0.45
    aldi
    0.45
     отношению
    0.42
    efits
    0.42
     despite
    0.42
    jinal
    0.42
    alc
    0.42
     trotz
    0.41
     funny
    0.41
    Activations Density 0.677%

    No Known Activations