© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142336
    Prev
    Next
    INDEX
    Explanations

    dwarfed by

    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_0_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
    >
    1.58
    는
    1.34
     insolvent
    1.22
    <
    1.18
    E
    1.13
    ]
    1.13
    ።
    1.13
    は
    1.11
    \
    1.10
    H
    1.09
    POSITIVE LOGITS
    то
    2.14
    า
    1.94
    et
    1.84
    q
    1.77
    ن
    1.77
    ס
    1.72
    to
    1.71
    ts
    1.71
    ten
    1.67
    re
    1.66
    Activations Density 0.001%

    No Known Activations