© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159988
    Prev
    Next
    INDEX
    Explanations

    nicknames

    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
    دی
    1.18
    見
    1.15
    ご
    1.08
    ला
    1.06
     राष्ट्र
    1.06
    いて
    1.05
    یده
    1.05
    st
    1.02
    いた
    1.02
    زی
    1.02
    POSITIVE LOGITS
    ە
    1.26
    ي
    1.25
    ים
    1.13
    ٠
    1.09
     in
    1.05
    1.05
     doctrines
    1.04
     كلمات
    1.04
     adjectives
    1.03
    т
    1.03
    Activations Density 0.001%

    No Known Activations