© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16140
    Prev
    Next
    INDEX
    Explanations

    a variety of function names, code snippets, dates, and specialized terms seemingly associated with computer-related contexts and medical procedures.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     समीक्षाओं
    -0.32
    };*/
    -0.30
    tanleria
    -0.29
     OFDb
    -0.27
    Datuak
    -0.27
    "):
    -0.27
     незавершена
    -0.27
     InputDecoration
    -0.26
    '):
    -0.26
    "]);
    -0.26
    POSITIVE LOGITS
    <bos>
    0.73
    BASEPATH
    0.45
    eqn
    0.39
    MENAFN
    0.39
     consultato
    0.36
    +:+
    0.36
    saraba
    0.35
     createState
    0.33
     Olms
    0.33
    OnAdd
    0.33
    Activations Density 11.266%

    No Known Activations