© 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. 142342
    Prev
    Next
    INDEX
    Explanations

    \t character in code

    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
    :
    1.62
    s
    1.45
     be
    1.41
    )
    1.35
    8
    1.30
     in
    1.27
    (
    1.27
    el
    1.26
    4
    1.25
    2
    1.24
    POSITIVE LOGITS
    ı
    1.22
    ية
    1.14
    υτό
    1.10
    ла
    1.07
    ур
    1.05
    他对
    1.02
    𝓪
    1.02
    мо
    1.02
    يس
    1.02
    ী
    1.01
    Activations Density 0.003%

    No Known Activations