© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205342
    Prev
    Next
    INDEX
    Explanations

    plan

    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
     ਦਾ
    0.44
    ospor
    0.42
    ந்தார்
    0.42
    땃
    0.41
     drawable
    0.40
    jasama
    0.39
    ordine
    0.39
     Rounded
    0.38
    कन्या
    0.38
    imak
    0.38
    POSITIVE LOGITS
     enhancing
    0.40
    錦
    0.39
    Keb
    0.39
     modifying
    0.38
    Int
    0.37
    Preparing
    0.37
    enhancing
    0.37
    )++;
    0.36
    Introduction
    0.36
    둠
    0.36
    Activations Density 0.001%

    No Known Activations