© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51236
    Prev
    Next
    INDEX
    Explanations

    E

    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_55_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
     ／
    0.45
    рое
    0.40
    ેશન
    0.38
    dal
    0.38
    <0x04>
    0.37
    θούν
    0.37
    dag
    0.37
    draft
    0.36
     जातो
    0.36
    乘
    0.36
    POSITIVE LOGITS
    ven
    0.81
    VEN
    0.71
    vent
    0.68
    veni
    0.66
    Ven
    0.64
    VENT
    0.63
    valuate
    0.59
    vena
    0.59
    vents
    0.56
     ven
    0.55
    Activations Density 0.001%

    No Known Activations