© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144022
    Prev
    Next
    INDEX
    Explanations

    more like

    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_0_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
    1.83
    ),
    1.46
    )
    1.45
    :
    1.21
    ;
    1.20
     by
    1.19
    ?),
    1.19
    ).”
    1.19
     of
    1.15
    )…
    1.13
    POSITIVE LOGITS
    in
    1.86
    ية
    1.80
    ли
    1.70
    م
    1.63
    на
    1.59
    м
    1.59
    يد
    1.52
    то
    1.51
    с
    1.48
    ти
    1.46
    Activations Density 0.007%

    No Known Activations