© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182826
    Prev
    Next
    INDEX
    Explanations

    caveats and disclaimers

    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
    XV
    0.41
    പ്
    0.40
    𝔦
    0.38
    𝓷
    0.38
     putem
    0.37
     grado
    0.37
    ksiyon
    0.37
    이스
    0.37
    <0x98>
    0.36
    कामा
    0.36
    POSITIVE LOGITS
    রোপ
    0.38
     cigar
    0.37
     Ell
    0.36
     Tad
    0.35
     ellipt
    0.35
    តិ
    0.35
     idiots
    0.35
     אמ
    0.35
    expand
    0.34
     enlarge
    0.34
    Activations Density 0.004%

    No Known Activations