© 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. 157904
    Prev
    Next
    INDEX
    Explanations

    relates to or has

    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
    al
    1.19
    ч
    1.12
    ور
    1.10
    يد
    1.10
    ৩
    1.04
    وريا
    1.03
    ัง
    1.02
    ায়
    1.02
    ين
    1.01
    он
    1.00
    POSITIVE LOGITS
     was
    1.56
    ج
    1.36
    し
    1.28
    ر
    1.24
    ه
    1.23
    t
    1.20
    ä
    1.15
    .
    1.13
    ได้
    1.10
    the
    1.05
    Activations Density 0.001%

    No Known Activations