© 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. 68714
    Prev
    Next
    INDEX
    Explanations

    names places entities

    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
     Five
    0.43
     五
    0.40
    Wein
    0.39
     Six
    0.39
    Five
    0.38
     Short
    0.38
    bett
    0.38
    𒁕
    0.37
    ][-
    0.37
    ಮೆ
    0.37
    POSITIVE LOGITS
     nausea
    0.41
    sup
    0.40
     harmony
    0.39
     supp
    0.39
    hide
    0.38
     aps
    0.38
    重ね
    0.37
     sup
    0.37
    к
    0.37
    __)
    0.36
    Activations Density 0.016%

    No Known Activations