© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175090
    Prev
    Next
    INDEX
    Explanations

    titles like President/King followed by names or punctuation

    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_20_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
    uriken
    0.43
    like
    0.43
     مانند
    0.38
    lichess
    0.38
    스러운
    0.38
    ૮
    0.37
    ترین
    0.37
     dikdört
    0.36
    ered
    0.35
    唦
    0.35
    POSITIVE LOGITS
     caso
    0.43
     Spitz
    0.40
     heinous
    0.39
     inquiry
    0.39
     accusing
    0.39
     finals
    0.38
     deactivated
    0.38
     cazul
    0.38
     Deutschland
    0.37
     issued
    0.37
    Activations Density 0.000%

    No Known Activations