© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198635
    Prev
    Next
    INDEX
    Explanations

    envisioning something

    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_9_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
    N
    0.48
    CTE
    0.45
    枕
    0.45
    ειας
    0.44
    Mn
    0.44
    SA
    0.43
    IZ
    0.43
    NCH
    0.42
    PA
    0.42
    ORTYPE
    0.42
    POSITIVE LOGITS
    ٹ
    0.52
     newbie
    0.51
     attacking
    0.49
    rap
    0.48
     beginner
    0.48
    ка
    0.47
    rebbero
    0.47
     novelists
    0.47
     newbies
    0.46
    ڑھ
    0.46
    Activations Density 0.000%

    No Known Activations