© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83019
    Prev
    Next
    INDEX
    Explanations

    Elasticsearch search

    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_0_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
    ר
    1.35
     inverso
    1.17
    ATION
    1.13
    ↵↵
    1.13
    ל
    1.11
    ਆਂ
    1.07
    ă
    1.05
    ąd
    1.04
    ви
    1.02
    ють
    1.02
    POSITIVE LOGITS
     on
    1.38
    .
    1.27
    na
    1.23
    on
    1.22
    st
    1.21
     ऑन
    1.20
    res
    1.18
    ان
    1.17
    主题
    1.17
    jší
    1.16
    Activations Density 0.000%

    No Known Activations