© 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. 157392
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    ו
    1.72
    ס
    1.45
    ד
    1.33
     I
    1.29
    י
    1.26
     M
    1.23
     L
    1.20
     S
    1.18
     G
    1.18
     D
    1.16
    POSITIVE LOGITS
    .
    1.48
     hvilket
    1.10
     destac
    1.05
     größ
    1.03
     mikä
    0.99
    <0xA0>
    0.97
    '
    0.96
     frais
    0.95
     contribu
    0.93
     torno
    0.92
    Activations Density 0.000%

    No Known Activations