© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3481
    Prev
    Next
    INDEX
    Explanations

    program code referencing a player entity

    oai_token-act-pair · gemini-2.0-flash

    Player

    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
     Shakspeare
    -0.73
    ükemmel
    -0.69
     responsabilità
    -0.68
    DockStyle
    -0.67
     tekem
    -0.66
     coppia
    -0.65
     kvinna
    -0.65
     scienza
    -0.64
     segni
    -0.63
     blessures
    -0.63
    POSITIVE LOGITS
    >}
    0.69
    >`
    0.68
    )">
    0.68
    }))
    0.66
    ?>">
    0.63
    ')}}">
    0.63
    })]
    0.62
    '],$
    0.62
     Liar
    0.62
    >")
    0.61
    Activations Density 0.470%

    No Known Activations