© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200462
    Prev
    Next
    INDEX
    Explanations

    single

    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_46_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
    Uni
    0.45
     uni
    0.44
    Dictionary
    0.44
    ECH
    0.44
    Lav
    0.43
     Dictionary
    0.41
    旨
    0.40
    uni
    0.40
     Uni
    0.40
    ]</
    0.39
    POSITIVE LOGITS
    sampled
    0.44
    boxed
    0.40
     fused
    0.36
    structured
    0.36
    ಸು
    0.36
     assortment
    0.35
     downed
    0.35
     የተ
    0.35
     ট
    0.35
     мг
    0.35
    Activations Density 0.000%

    No Known Activations