© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141678
    Prev
    Next
    INDEX
    Explanations

    understood

    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_12_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
    b
    0.67
    ارق
    0.64
    +
    0.59
    up
    0.58
    utung
    0.54
    ̵
    0.54
    ſ
    0.53
    et
    0.52
    afa
    0.52
    т
    0.52
    POSITIVE LOGITS
     resulta
    0.57
     articol
    0.55
     indicado
    0.55
     entraîner
    0.55
     sociais
    0.54
     escrever
    0.54
     নিঃসৃত
    0.54
    ᆯ
    0.54
    ﻖ
    0.54
     calcula
    0.54
    Activations Density 0.001%

    No Known Activations