© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202821
    Prev
    Next
    INDEX
    Explanations

    palaces and consonants

    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_12_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
     corta
    0.55
     confer
    0.54
     Confer
    0.52
    నాన్ని
    0.52
     tệ
    0.52
    醸
    0.52
     Banca
    0.51
     Mani
    0.50
     conferencing
    0.49
     Manly
    0.49
    POSITIVE LOGITS
    jne
    0.58
    ٢
    0.57
    Amount
    0.57
    atu
    0.52
    ajoz
    0.52
    force
    0.52
    kes
    0.50
    acie
    0.50
    fort
    0.50
     *)
    0.49
    Activations Density 0.000%

    No Known Activations