© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141089
    Prev
    Next
    INDEX
    Explanations

    inner monologue

    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_12_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
     dicta
    0.45
    יין
    0.45
     назвать
    0.45
     "-"]
    0.42
     postal
    0.42
     spicy
    0.42
     resulted
    0.41
    ậc
    0.40
    </sub>
    0.40
     cuis
    0.40
    POSITIVE LOGITS
    data
    0.59
    Aula
    0.51
    api
    0.49
    Tourism
    0.47
    lire
    0.47
    数据
    0.46
    hold
    0.44
    pling
    0.44
    luft
    0.44
    Wrist
    0.44
    Activations Density 0.003%

    No Known Activations