© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81558
    Prev
    Next
    INDEX
    Explanations

    som followed by completion

    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
    का
    1.43
    𝗦
    1.27
    iv
    1.21
    个
    1.20
    Ֆ
    1.15
    सीएल
    1.13
    터
    1.13
    OV
    1.12
    ation
    1.11
     média
    1.11
    POSITIVE LOGITS
    f
    1.75
    v
    1.59
    ৭
    1.56
    ד
    1.46
    c
    1.42
    ן
    1.42
    de
    1.37
    р
    1.37
    st
    1.30
    \%
    1.29
    Activations Density 0.000%

    No Known Activations