© 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. 105900
    Prev
    Next
    INDEX
    Explanations

    major

    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
    g
    1.43
    i
    1.41
    l
    1.36
    1
    1.35
    B
    1.30
    The
    1.26
    ت
    1.21
    r
    1.20
    y
    1.20
    d
    1.19
    POSITIVE LOGITS
     be
    1.23
     are
    1.19
    ة
    1.03
     can
    1.00
     on
    0.99
    та
    0.96
    ă
    0.96
     र
    0.96
    นา
    0.96
    માં
    0.96
    Activations Density 0.000%

    No Known Activations