© 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. 61429
    Prev
    Next
    INDEX
    Explanations

    gosh

    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
    го
    1.16
    ),
    1.14
    )،
    1.14
     Executes
    1.06
    ە
    1.03
    )
    1.02
    ست
    1.01
     They
    1.00
     Improves
    1.00
     DON
    0.98
    POSITIVE LOGITS
    л
    1.52
    ل
    1.45
     κά
    1.24
    imą
    1.23
    ル
    1.20
    ни
    1.19
     immobil
    1.19
    .
    1.09
    liness
    1.08
    r
    1.07
    Activations Density 0.002%

    No Known Activations