© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86468
    Prev
    Next
    INDEX
    Explanations

    must have

    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_18_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
    认知
    0.32
    Believe
    0.31
     গার্ডিয়ান
    0.29
     لازم
    0.28
    烦
    0.28
    乐
    0.28
    ］
    0.28
    䍧
    0.28
    Parts
    0.28
     meilleures
    0.28
    POSITIVE LOGITS
    m
    0.36
    abt
    0.36
     receptors
    0.33
     reméd
    0.32
    apet
    0.31
    antes
    0.31
    ukat
    0.31
    avak
    0.30
    iri
    0.29
    ovič
    0.29
    Activations Density 0.006%

    No Known Activations