© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206467
    Prev
    Next
    INDEX
    Explanations

    opening brackets

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Ï
    0.37
     остается
    0.37
     exp
    0.35
     ina
    0.34
    wind
    0.34
    śnie
    0.34
    획
    0.34
     ent
    0.33
     leaves
    0.33
     izquier
    0.33
    POSITIVE LOGITS
    成了
    0.41
     dugg
    0.41
    腃
    0.39
     \%\
    0.39
    Contrib
    0.38
     সভ
    0.38
     ',');
    0.38
    ोरेंट
    0.38
    );//
    0.38
     অ্যান
    0.38
    Activations Density 0.001%

    No Known Activations