© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46693
    Prev
    Next
    INDEX
    Explanations

    NCERT and n-grams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    t
    0.76
    l
    0.71
     choppy
    0.66
    𝘢
    0.66
    oną
    0.63
    কে
    0.62
     coeficiente
    0.62
     transistor
    0.60
     plante
    0.59
     PST
    0.58
    POSITIVE LOGITS
    de
    0.68
    vis
    0.68
    ]
    0.62
    phthal
    0.61
    $
    0.61
    be
    0.61
    jm
    0.60
    س
    0.59
    ని
    0.57
    blica
    0.57
    Activations Density 0.000%

    No Known Activations