© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111230
    Prev
    Next
    INDEX
    Explanations

    Dordogne, aldehyde, Alhamdulillah

    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
    AN
    1.39
    AK
    1.15
    AE
    1.14
    p
    1.14
     a
    1.13
    a
    1.12
    IK
    1.11
    EN
    1.09
    AL
    1.09
    AG
    1.09
    POSITIVE LOGITS
    ش
    1.51
    մ
    1.30
    ş
    1.25
    ш
    1.11
    ط
    1.10
     mắt
    0.97
     horno
    0.97
    ف
    0.97
    汅
    0.97
    اء
    0.93
    Activations Density 0.000%

    No Known Activations