© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192690
    Prev
    Next
    INDEX
    Explanations

    conditional, temporal, or comparative statements

    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_4_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
    et
    1.48
    -
    1.10
    ies
    1.09
    ية
    1.09
    ized
    1.07
    ado
    1.04
    in
    1.03
    ie
    1.03
    ett
    1.03
    !
    0.99
    POSITIVE LOGITS
    цата
    0.96
     swoich
    0.93
     eğ
    0.92
     conceivably
    0.91
    例えば
    0.88
     adjudged
    0.84
     oure
    0.84
     overjoyed
    0.84
     svojih
    0.82
    𝓽
    0.82
    Activations Density 0.082%

    No Known Activations