© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203891
    Prev
    Next
    INDEX
    Explanations

    list items, bullet points, or code blocks

    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_25_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
     Geißler
    0.25
     نسخ
    0.24
    forschungs
    0.23
    RuL
    0.23
    Dok
    0.22
    untungan
    0.22
    辈子
    0.22
    )|$(
    0.22
     Сак
    0.22
     например
    0.22
    POSITIVE LOGITS
     tankers
    0.27
     flannel
    0.26
     encomendas
    0.26
     remer
    0.25
    ELSE
    0.25
    Jasper
    0.25
    되고
    0.25
     divisional
    0.25
     legs
    0.25
     perme
    0.25
    Activations Density 0.011%

    No Known Activations