© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53292
    Prev
    Next
    INDEX
    Explanations

    offering options

    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_55_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
     Picking
    0.45
     Note
    0.41
    宻
    0.40
     Strongly
    0.39
    Compose
    0.39
    identical
    0.38
    ตาล
    0.38
     note
    0.37
     नोट
    0.37
    ἲ
    0.37
    POSITIVE LOGITS
    坞
    0.36
     với
    0.35
    ೊಂದಿಗೆ
    0.35
    with
    0.33
     with
    0.33
    ZQ
    0.32
    我们将
    0.32
     kanssa
    0.31
    productions
    0.31
    joins
    0.31
    Activations Density 0.054%

    No Known Activations