© 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. 62402
    Prev
    Next
    INDEX
    Explanations

    gradual transition or changes

    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
    و
    1.35
    이었
    1.34
    ்கள்
    1.21
    นี
    1.19
    у
    1.16
    де
    1.16
    यों
    1.16
    u
    1.15
    이니까
    1.14
    é
    1.14
    POSITIVE LOGITS
    ट
    1.38
    غ
    1.24
    ח
    1.16
     a
    1.14
    之为
    1.14
     as
    1.11
     is
    1.07
     fortale
    1.07
    場合
    1.06
    ول
    1.05
    Activations Density 0.000%

    No Known Activations