© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205112
    Prev
    Next
    INDEX
    Explanations

    John

    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
     sector
    0.41
     इक्
    0.38
    原始内容存档于
    0.38
     LoggerFactory
    0.37
    IBAction
    0.37
    ครัว
    0.36
     clog
    0.36
    側
    0.36
    गुर
    0.36
    業務用
    0.35
    POSITIVE LOGITS
     Akar
    0.40
    orty
    0.37
    íta
    0.37
     Jake
    0.37
     Paxton
    0.36
     inverse
    0.36
    Kurt
    0.36
    iane
    0.35
    elastic
    0.34
     roused
    0.34
    Activations Density 0.000%

    No Known Activations