© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89334
    Prev
    Next
    INDEX
    Explanations

    It is

    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_23_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
     клавиа
    0.15
    AspNetCore
    0.15
    ]";
    0.14
     вчера
    0.14
     рецен
    0.14
    扩张
    0.13
    сера
    0.13
     цере
    0.13
    reira
    0.13
     OpenAI
    0.13
    POSITIVE LOGITS
    ney
    0.16
     guarant
    0.16
    ły
    0.16
    tble
    0.16
    mov
    0.16
    ują
    0.16
     없이
    0.16
    饞
    0.16
    key
    0.16
     ಕಟ್ಟ
    0.16
    Activations Density 0.054%

    No Known Activations