© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    the word "studio," sometimes with a modifier like "usually"

    oai_token-act-pair · gemini-2.0-flash

    studio

    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
    RenderAtEndOf
    -0.77
    en
    -0.66
    et
    -0.65
    al
    -0.57
    na
    -0.57
    ̈
    -0.54
    i
    -0.54
    >';
    -0.53
     }));
    -0.53
    men
    -0.53
    POSITIVE LOGITS
    NUMX
    1.02
    <bos>
    0.98
    ollary
    0.86
    tvguidetime
    0.84
    andaag
    0.84
    knecht
    0.82
    ftance
    0.81
    nicity
    0.80
    frastructure
    0.79
    lecular
    0.79
    Activations Density 1.665%

    No Known Activations