© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    legal and political discourse, including agreements, testimonies, allegations and immigration.

    oai_token-act-pair · gemini-2.0-flash

    accept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     acceptance
    -1.27
     Acceptance
    -1.20
     accepts
    -1.19
     accepted
    -1.16
     accept
    -1.15
    Acceptance
    -1.08
     ACCEPT
    -1.05
    acceptance
    -1.05
     Accepted
    -1.05
    accept
    -1.05
    POSITIVE LOGITS
     تانيه
    0.72
     Roskov
    0.67
    ]").
    0.66
     Infórmanos
    0.65
    hdysval
    0.64
    voici
    0.63
     '\\;'
    0.63
     gainera
    0.63
    ."</
    0.63
    ()]
    0.63
    Activations Density 22.845%

    No Known Activations