© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195955
    Prev
    Next
    INDEX
    Explanations

    options after a letter

    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_27_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
     Muit
    0.38
     mitt
    0.37
     सदस्यीय
    0.37
     Η
    0.37
     Αυ
    0.37
    otted
    0.36
     Ин
    0.36
     BON
    0.36
     RADI
    0.36
     BET
    0.36
    POSITIVE LOGITS
    ūk
    0.41
    ্কর
    0.37
    ObjData
    0.36
     grabs
    0.35
    uli
    0.35
     converge
    0.35
    善
    0.35
    kins
    0.34
    शिता
    0.34
     plausible
    0.34
    Activations Density 0.000%

    No Known Activations