© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14074
    Prev
    Next
    INDEX
    Explanations

    short phrases or clauses

    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_13_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
    r
    0.33
    s
    0.29
    be
    0.27
    Brother
    0.27
    was
    0.26
    ut
    0.26
    ra
    0.25
    to
    0.25
    ona
    0.25
    N
    0.25
    POSITIVE LOGITS
    ୟ
    0.27
     chairperson
    0.25
     एक्चु
    0.25
     esters
    0.25
     fullname
    0.25
     penyakit
    0.24
     Geräte
    0.23
     químicos
    0.23
     secteurs
    0.23
     spost
    0.23
    Activations Density 0.472%

    No Known Activations