© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180031
    Prev
    Next
    INDEX
    Explanations

    `corpora` and `token`

    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_24_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
    зво
    0.38
     Réponses
    0.38
     enthält
    0.37
     выглядит
    0.37
     Maul
    0.37
     Aluminum
    0.37
    <unused18>
    0.36
     ваша
    0.36
    воль
    0.36
    ರೋ
    0.35
    POSITIVE LOGITS
     agora
    0.42
     estates
    0.39
    ष्‍ट
    0.39
    披
    0.39
     ora
    0.37
     staking
    0.37
    doFilter
    0.37
    +:
    0.37
    }},
    0.37
    蔬
    0.37
    Activations Density 0.000%

    No Known Activations