© 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. 150748
    Prev
    Next
    INDEX
    Explanations

    next door

    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
     sorely
    0.50
    enie
    0.49
    зовы
    0.48
    ቮ
    0.45
    ନ
    0.44
     conso
    0.44
     Küh
    0.44
     csr
    0.44
    erden
    0.44
    2
    0.44
    POSITIVE LOGITS
     defenses
    0.44
    į
    0.42
    í
    0.42
    тельная
    0.42
    centroids
    0.40
    infiltration
    0.40
    agiarism
    0.40
    יה
    0.40
    tra
    0.39
    ības
    0.39
    Activations Density 0.000%

    No Known Activations