© 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. 168422
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
     .=
    0.41
     $=$
    0.40
    .#
    0.37
    .=
    0.37
    ).*
    0.36
    )."
    0.36
     SPIN
    0.36
     ".")
    0.36
    ewana
    0.35
    鲵
    0.35
    POSITIVE LOGITS
    」
    0.38
     」
    0.37
    `
    0.36
     froze
    0.33
    adiyah
    0.32
     Rape
    0.32
    贱
    0.32
    〃
    0.32
     』
    0.32
    kernels
    0.32
    Activations Density 0.003%

    No Known Activations