© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37958
    Prev
    Next
    INDEX
    Explanations

    benzyl alcohol, chloride, XVI

    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_3_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
    le
    1.13
    1
    1.11
    on
    1.02
    li
    1.02
    (
    1.01
    at
    0.96
    la
    0.95
    ли
    0.94
    t
    0.94
    ere
    0.92
    POSITIVE LOGITS
     projeto
    0.91
     termine
    0.91
     conceito
    0.88
     maggio
    0.88
     criterio
    0.88
    ち
    0.87
     دلیل
    0.86
     lintas
    0.85
     dominio
    0.84
     sytuacji
    0.84
    Activations Density 0.000%

    No Known Activations