© 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. 112726
    Prev
    Next
    INDEX
    Explanations

    parts of words, especially in other languages

    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
     intercom
    1.15
     intestate
    1.14
    in
    1.13
     indeterminate
    1.05
    리
    1.05
    ری
    1.04
     invertible
    1.03
    𝗖
    1.03
     itinéraires
    1.02
     imperme
    1.01
    POSITIVE LOGITS
    м
    1.38
    ä
    1.35
    j
    1.30
    م
    1.23
    z
    1.11
    л
    1.10
    b
    1.07
    р
    1.07
    的关键
    1.02
    f
    1.01
    Activations Density 0.000%

    No Known Activations