© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197413
    Prev
    Next
    INDEX
    Explanations

    number of ways to

    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_4_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
    a
    0.23
    I
    0.19
    '
    0.18
    n
    0.16
    ;
    0.15
    o
    0.15
    i
    0.14
    nál
    0.14
    f
    0.14
    :
    0.13
    POSITIVE LOGITS
    ز
    0.16
    м
    0.14
    ט
    0.13
    תו
    0.12
    વ
    0.12
    ლ
    0.12
    т
    0.12
    ย
    0.12
    م
    0.11
    𝐭
    0.11
    Activations Density 0.040%

    No Known Activations