© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200506
    Prev
    Next
    INDEX
    Explanations

    Navigator, letter, Ranking

    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_12_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
     petal
    0.50
     Nobel
    0.48
     mùi
    0.47
    це
    0.45
    \/
    0.44
    挂
    0.44
    те
    0.44
    нак
    0.44
    玽
    0.43
     على
    0.43
    POSITIVE LOGITS
     ambulances
    0.57
     Dixon
    0.55
     kereta
    0.55
    ARDS
    0.53
    usting
    0.53
    rd
    0.52
    Cumm
    0.52
    onnées
    0.51
    weeks
    0.50
    According
    0.50
    Activations Density 0.001%

    No Known Activations