© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175864
    Prev
    Next
    INDEX
    Explanations

    extracting filenames

    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
    ia
    0.53
     elsewhere
    0.46
    í
    0.44
    aba
    0.40
    bu
    0.40
    Data
    0.39
    itime
    0.39
    iance
    0.39
    Elsewhere
    0.38
    e
    0.38
    POSITIVE LOGITS
    ソル
    0.46
    τές
    0.45
    䜌
    0.45
     சுற்றுச்சூழல்
    0.44
     vattum
    0.43
    לה
    0.43
    ्टर
    0.42
    樂
    0.42
    ਕੇ
    0.41
    ਟ
    0.41
    Activations Density 0.001%

    No Known Activations