© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13272
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to something being typical or common, along with some seemingly unrelated words.

    oai_token-act-pair · gemini-2.0-flash

    indoor or usual descriptions

    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
     متعلقه
    -1.13
     NSCoder
    -1.12
    istoitu
    -1.10
    ArgsConstructor
    -1.09
    UserScript
    -1.05
    tvguidetime
    -1.05
    NUMX
    -1.05
    ]--;
    -1.04
    makeConstraints
    -1.02
    ReusableCell
    -1.02
    POSITIVE LOGITS
    <bos>
    2.16
    '
    1.21
    ↵↵
    1.09
    ’
    1.04
    a
    0.91
    -
    0.87
    s
    0.85
    1
    0.83
    The
    0.81
    2
    0.78
    Activations Density 1.597%

    No Known Activations