© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157925
    Prev
    Next
    INDEX
    Explanations

    PBKDF2 key derivation

    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_2_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
    u
    1.45
    大
    1.38
    h
    1.34
    و
    1.20
    m
    1.19
    د
    1.19
    म
    1.18
    hava
    1.15
    他对
    1.12
    te
    1.08
    POSITIVE LOGITS
    ᱴ
    0.99
     stomachs
    0.98
    ’
    0.98
    ﻫ
    0.94
    ۹
    0.93
     khuẩn
    0.92
     вій
    0.91
     inductance
    0.91
    ão
    0.90
     смесь
    0.90
    Activations Density 0.000%

    No Known Activations