© 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. 160967
    Prev
    Next
    INDEX
    Explanations

    Sandro, Ananda, Nanda

    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
    ent
    1.52
     I
    1.45
    ية
    1.45
    a
    1.42
    ում
    1.40
    el
    1.38
    e
    1.33
    ed
    1.25
    iD
    1.20
    p
    1.19
    POSITIVE LOGITS
    the
    1.48
    ب
    1.43
    نا
    1.33
    3
    1.27
    that
    1.21
    .
    1.21
     that
    1.17
    ס
    1.16
    ق
    1.13
    וד
    1.09
    Activations Density 0.000%

    No Known Activations