© 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. 176643
    Prev
    Next
    INDEX
    Explanations

    license number

    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
    ø
    0.66
    ir
    0.59
    ød
    0.57
    ting
    0.56
    øk
    0.56
    uah
    0.56
    ut
    0.53
    ijnlijk
    0.52
    ö
    0.52
    åg
    0.51
    POSITIVE LOGITS
    ເ
    0.53
     ಆ
    0.47
     வர
    0.46
    ﻬ
    0.44
     વા
    0.44
     caball
    0.44
     thrice
    0.44
     sencillo
    0.43
    滑
    0.41
    esquerdo
    0.41
    Activations Density 0.000%

    No Known Activations