© 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-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181404
    Prev
    Next
    INDEX
    Explanations

    python code and related libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    畱
    0.36
     photometric
    0.36
    Boxing
    0.36
    ದಯ
    0.35
    UserModel
    0.35
    दारा
    0.35
    াইয়৷
    0.34
    電視劇
    0.34
    NgramModel
    0.33
    給你
    0.33
    POSITIVE LOGITS
    geist
    0.36
    п
    0.35
     –
    0.35
    ’
    0.34
     haven
    0.32
    <0xE2>
    0.31
     advancements
    0.31
    cod
    0.31
    xyz
    0.30
    °,
    0.30
    Activations Density 0.001%

    No Known Activations