© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206772
    Prev
    Next
    INDEX
    Explanations

    remain

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     left
    3.70
    left
    3.28
     Left
    3.17
    左
    3.11
    Left
    3.09
     LEFT
    2.83
     izquierda
    2.69
     左
    2.69
    LEFT
    2.63
     esquerda
    2.55
    POSITIVE LOGITS
    所在的
    0.34
    uttosto
    0.33
     Regl
    0.33
    risch
    0.32
     })(
    0.31
    schw
    0.31
    亗
    0.31
    gador
    0.31
    ськ
    0.30
    ensem
    0.30
    Activations Density 0.008%

    No Known Activations