© 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. 205223
    Prev
    Next
    INDEX
    Explanations

    din

    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
    ڏ
    0.42
    梸
    0.39
    esehatan
    0.39
    grader
    0.38
     හැකිය
    0.38
    walle
    0.38
     Martínez
    0.38
    ዢ
    0.37
    èles
    0.37
    Zx
    0.37
    POSITIVE LOGITS
    remia
    0.38
    glial
    0.37
     kimchi
    0.37
     spraw
    0.36
    νου
    0.36
     frag
    0.35
    विदा
    0.35
    州
    0.35
     caterpillar
    0.35
    atical
    0.35
    Activations Density 0.000%

    No Known Activations