© 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. 176580
    Prev
    Next
    INDEX
    Explanations

    numbers, counts, ranges

    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
     wellbeing
    0.41
    耱
    0.38
     trazendo
    0.38
    etten
    0.37
    ască
    0.37
     với
    0.36
    '))->
    0.35
     để
    0.35
    obe
    0.35
     tại
    0.35
    POSITIVE LOGITS
     før
    0.41
    ତା
    0.40
    긴
    0.39
    長い
    0.37
    古い
    0.36
    Before
    0.36
    ISTS
    0.35
    ムー
    0.35
    зову
    0.35
    before
    0.34
    Activations Density 0.002%

    No Known Activations