© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77712
    Prev
    Next
    INDEX
    Explanations

    '

    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_53_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
    mbito
    0.42
    lub
    0.39
     gay
    0.38
    蔼
    0.38
    tall
    0.38
    krit
    0.37
    hug
    0.37
    lab
    0.36
     histoire
    0.36
    医
    0.36
    POSITIVE LOGITS
    수에
    0.40
    innam
    0.39
     Di
    0.39
     NAB
    0.38
     kc
    0.38
    Di
    0.38
     diaphrag
    0.37
     Broker
    0.37
     دی
    0.36
    ^{*}(
    0.36
    Activations Density 0.000%

    No Known Activations