© 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. 58164
    Prev
    Next
    INDEX
    Explanations

    tomes

    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
    ید
    1.28
    ﻔ
    1.10
    ур
    1.04
    ۴
    1.03
    ၄
    1.02
    ᱔
    1.02
    mml
    1.01
    ᱗
    0.99
    wavelength
    0.98
    nance
    0.96
    POSITIVE LOGITS
    ס
    1.18
    ד
    1.15
    ן
    1.10
    ल
    0.98
    ע
    0.97
    פ
    0.96
    ي
    0.93
    ל
    0.93
     पड़ेगा
    0.92
    మ
    0.92
    Activations Density 0.000%

    No Known Activations