© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157624
    Prev
    Next
    INDEX
    Explanations

    Ackerman

    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_2_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
     as
    1.55
    다
    1.46
    いた
    1.30
    их
    1.28
    یت
    1.23
    них
    1.22
    ル
    1.21
    痍
    1.19
    ی
    1.17
    نی
    1.15
    POSITIVE LOGITS
    ла
    1.75
    1.49
    -
    1.41
    ’
    1.41
    r
    1.11
    ore
    1.10
    w
    1.09
    mod
    1.08
    iv
    1.07
    '
    1.07
    Activations Density 0.000%

    No Known Activations