© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14095
    Prev
    Next
    INDEX
    Explanations

    the Danish language

    oai_token-act-pair · gemini-2.0-flash

    people's descriptions

    np_max-act-logits · 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
    скоп
    -0.44
     lccn
    -0.43
    Tracce
    -0.43
    タリー
    -0.41
    W
    -0.40
    ter
    -0.40
    حيان
    -0.40
    verifier
    -0.40
    IntoConstraints
    -0.40
    варь
    -0.39
    POSITIVE LOGITS
     endfor
    0.77
    ^(@)
    0.76
     beginnetje
    0.66
     Houſe
    0.64
     ―――――
    0.63
    CopyWith
    0.61
     nahilalakip
    0.59
    "],
    0.59
    $")
    0.58
    </thead>
    0.57
    Activations Density 0.809%

    No Known Activations