© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158864
    Prev
    Next
    INDEX
    Explanations

    Irving, Griffin

    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_2_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
    ות
    1.72
     about
    1.29
     on
    1.24
     sobre
    1.20
     zwischen
    1.19
     zacz
    1.14
    ৫
    1.13
     mezi
    1.10
     czasie
    1.09
     едно
    1.09
    POSITIVE LOGITS
    0
    1.44
    ne
    1.29
    I
    1.23
    ni
    1.20
    ssä
    1.20
    mias
    1.18
    pa
    1.17
    nger
    1.16
    ning
    1.13
    mma
    1.13
    Activations Density 0.000%

    No Known Activations