© 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. 112515
    Prev
    Next
    INDEX
    Explanations

    rendition

    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
    the
    1.23
    ים
    1.10
    ד
    0.96
    ;
    0.93
     antics
    0.93
    )(
    0.92
    ooo
    0.92
     gaskets
    0.91
    限于
    0.89
    you
    0.88
    POSITIVE LOGITS
    يل
    1.20
     as
    1.18
     have
    1.12
    ется
    1.11
    ación
    1.09
     Հ
    1.02
    ции
    1.01
    ν
    1.01
    ாலும்
    0.99
     destac
    0.98
    Activations Density 0.000%

    No Known Activations