© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    using System;

    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_13_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
     n
    0.21
    p
    0.20
    ворю
    0.20
     i
    0.19
    dL
    0.19
    User
    0.18
     unresolved
    0.18
    ке
    0.18
     locals
    0.17
    score
    0.17
    POSITIVE LOGITS
    ب
    0.24
    ار
    0.21
    مس
    0.21
    مش
    0.21
     Economy
    0.21
    ਈ
    0.21
    مت
    0.21
    isht
    0.20
     cambiamento
    0.20
    م
    0.20
    Activations Density 0.027%

    No Known Activations