© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132612
    Prev
    Next
    INDEX
    Explanations

    in, IN, or ín followed by something

    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
    ter
    1.27
    Re
    1.23
    of
    1.21
    1.20
    was
    1.18
    Be
    1.14
    Code
    1.13
    </h3>
    1.06
    னின்
    1.05
    over
    1.03
    POSITIVE LOGITS
    ,
    1.25
    دين
    0.95
     in
    0.95
     easements
    0.94
     fierc
    0.94
    ш
    0.94
     councils
    0.93
     dividends
    0.92
     bolstering
    0.92
     crossings
    0.91
    Activations Density 0.001%

    No Known Activations