© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134723
    Prev
    Next
    INDEX
    Explanations

    halter, Imitator, Führe, absuchen, formell

    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_1_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
    ۰
    1.26
     și
    1.13
     a
    1.12
     ו
    1.10
    に
    1.09
    ید
    1.08
    ۹
    1.02
     informó
    1.01
    ם
    1.00
     embroiled
    0.98
    POSITIVE LOGITS
    n
    1.87
    on
    1.39
    น
    1.28
    j
    1.27
    त
    1.26
    ре
    1.25
    e
    1.21
    ed
    1.20
    па
    1.20
    v
    1.19
    Activations Density 0.001%

    No Known Activations