© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 165516
    Prev
    Next
    INDEX
    Explanations

    code closing punctuation followed by comments

    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_34_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
    тавли
    0.44
     पाण्याची
    0.37
    ៕
    0.37
    ."]
    0.36
    𝓙
    0.36
    .*/
    0.36
     যাও
    0.35
    nju
    0.35
    teau
    0.35
    𝟯
    0.35
    POSITIVE LOGITS
     exclus
    0.44
    Wald
    0.39
     exclusivity
    0.37
     lég
    0.36
     المخ
    0.36
     atmosfé
    0.36
     perturb
    0.36
     guaranteeing
    0.35
     exclusivo
    0.35
     Lég
    0.35
    Activations Density 0.003%

    No Known Activations