© 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. 207361
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    Chang
    0.41
    PhD
    0.40
     prepar
    0.36
    LLB
    0.36
    ⓷
    0.36
     изго
    0.35
    phis
    0.35
    CHAN
    0.35
     PHD
    0.35
    ⓛ
    0.35
    POSITIVE LOGITS
     enggak
    0.42
     Dru
    0.39
     eva
    0.39
    ͚
    0.36
    /%
    0.36
     Evaluation
    0.36
    왔
    0.36
     belongs
    0.35
    bé
    0.35
    র্ত
    0.35
    Activations Density 0.000%

    No Known Activations