© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104384
    Prev
    Next
    INDEX
    Explanations

    pockets

    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_1_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
    un
    1.27
    с
    1.24
    к
    1.18
    ну
    1.17
    ير
    1.16
    т
    1.16
    м
    1.16
     Ко
    1.12
    на
    1.11
    не
    1.09
    POSITIVE LOGITS
    \
    1.16
    ,
    1.13
    )
    1.12
    К
    1.01
    Α
    0.96
     vlog
    0.96
    >
    0.95
     pikir
    0.94
     rulemaking
    0.92
     lingua
    0.91
    Activations Density 0.000%

    No Known Activations