© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59049
    Prev
    Next
    INDEX
    Explanations

    VERSATION

    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_2_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
    ী
    1.41
    ו
    1.38
    يها
    1.24
    ת
    1.19
    $,
    1.18
    ة
    1.15
    that
    1.14
    ак
    1.14
    ir
    1.12
    িক
    1.09
    POSITIVE LOGITS
     was
    1.22
    SA
    1.20
    p
    1.16
    šen
    1.05
    SER
    1.03
     leído
    1.02
    ved
    1.02
    žić
    1.00
    fe
    0.98
     në
    0.98
    Activations Density 0.001%

    No Known Activations