© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180276
    Prev
    Next
    INDEX
    Explanations

    same as

    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_24_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
    ziehen
    0.32
    ptides
    0.29
     इंजी
    0.28
    ।''
    0.27
    вью
    0.27
    撕
    0.26
    வ்
    0.26
     câncer
    0.26
     intensively
    0.26
    zieht
    0.26
    POSITIVE LOGITS
    별
    0.32
    UTA
    0.29
    Prospect
    0.28
     iner
    0.27
    uta
    0.27
    愷
    0.27
    IdentityProvider
    0.26
    Princ
    0.26
     DUR
    0.26
    မှတ်
    0.26
    Activations Density 0.055%

    No Known Activations