© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15315
    Prev
    Next
    INDEX
    Explanations

    many situations/cases

    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_15_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
    virus
    0.20
    ella
    0.19
    c
    0.19
    ectomy
    0.19
    elli
    0.17
    cy
    0.17
    危机
    0.17
    ell
    0.17
    ante
    0.17
    illa
    0.17
    POSITIVE LOGITS
     Panasonic
    0.20
     Toshiba
    0.18
    Panasonic
    0.17
    パナソニック
    0.17
     Sprach
    0.16
    NaOMe
    0.16
     Farb
    0.15
    맺
    0.15
    SIBLE
    0.15
     Elektr
    0.15
    Activations Density 0.097%

    No Known Activations