© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145157
    Prev
    Next
    INDEX
    Explanations

    ge gef ter Ге

    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_0_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
    u
    2.34
    d
    1.63
    daki
    1.62
    k
    1.59
    دا
    1.46
    ມັນ
    1.45
    w
    1.41
    dari
    1.41
    lr
    1.39
    t
    1.38
    POSITIVE LOGITS
    ↵↵
    1.96
     que
    1.60
    3
    1.59
    ை
    1.42
    6
    1.35
     deren
    1.34
    ｱ
    1.34
     do
    1.32
    5
    1.27
     quitar
    1.27
    Activations Density 0.000%

    No Known Activations