© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79322
    Prev
    Next
    INDEX
    Explanations

    Travel cards, credit cards, SIM cards

    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
    ﻛ
    1.32
    قف
    1.21
    ми
    1.20
    ますが
    1.15
    нын
    1.13
    нку
    1.13
    dır
    1.12
     کاغذ
    1.12
    э
    1.10
    ⲟ
    1.09
    POSITIVE LOGITS
    y
    2.39
    p
    2.30
    c
    2.11
    b
    2.11
    i
    2.08
    ed
    1.91
    n
    1.90
    an
    1.85
    RE
    1.73
    u
    1.70
    Activations Density 0.001%

    No Known Activations