© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177000
    Prev
    Next
    INDEX
    Explanations

    order of importance

    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
     الاولى
    0.50
    ਨ
    0.50
    ل
    0.47
    楇
    0.46
     فورم
    0.46
    Дан
    0.45
    zani
    0.45
    χρι
    0.44
    图案
    0.44
    財務
    0.44
    POSITIVE LOGITS
    처럼
    0.49
     like
    0.49
     s
    0.44
     sk
    0.43
     como
    0.43
     novel
    0.43
     seperti
    0.42
     multiplayer
    0.41
    Else
    0.41
    owanie
    0.41
    Activations Density 0.000%

    No Known Activations