© 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. 139912
    Prev
    Next
    INDEX
    Explanations

    post hoc, in situ

    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
    Nana
    0.52
     purporting
    0.48
     ار
    0.48
     amit
    0.48
     breaching
    0.47
    бир
    0.47
    ш
    0.47
     cerebellar
    0.46
     бо
    0.46
     disgraced
    0.46
    POSITIVE LOGITS
    EN
    0.65
    :
    0.60
    I
    0.59
     maks
    0.58
    IL
    0.53
    ts
    0.52
    ention
    0.52
    h
    0.52
    OGRAP
    0.52
    ting
    0.51
    Activations Density 0.000%

    No Known Activations