© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214848
    Prev
    Next
    INDEX
    Explanations

    harpsichord or harp

    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_5_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
    ar
    1.26
    c
    1.19
     castration
    1.13
     regrett
    1.12
    )
    1.05
     cautiously
    1.03
    g
    1.03
    al
    1.01
    arif
    1.00
    it
    1.00
    POSITIVE LOGITS
    л
    1.53
    ل
    1.48
    м
    1.44
    나
    1.22
    та
    1.21
    ল
    1.20
    ления
    1.17
    </h2>
    1.13
    to
    1.13
    ル
    1.13
    Activations Density 0.000%

    No Known Activations