© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106429
    Prev
    Next
    INDEX
    Explanations

    clogged or backlog

    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_1_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
    .
    1.64
     are
    1.51
    é
    1.34
    ;
    1.23
    6
    1.23
    es
    1.19
     considère
    1.18
    :
    1.18
    は
    1.18
     není
    1.16
    POSITIVE LOGITS
    X
    1.08
     Tokens
    1.02
    W
    1.01
    ﻥ
    1.01
     Substit
    0.99
    the
    0.98
    I
    0.97
    A
    0.96
     Surplus
    0.96
     Distrib
    0.95
    Activations Density 0.000%

    No Known Activations