© 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. 178957
    Prev
    Next
    INDEX
    Explanations

    fstream content operations

    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
    Thin
    0.49
    మ్
    0.46
     headspace
    0.43
     disrespectful
    0.43
    Мі
    0.42
     정보를
    0.42
     smart
    0.41
    珩
    0.41
    cısı
    0.41
    Fog
    0.40
    POSITIVE LOGITS
     arque
    0.41
    <?
    0.38
    よく
    0.38
     quedando
    0.38
    ocentric
    0.37
     понятно
    0.37
     donde
    0.36
    良く
    0.36
     facilmente
    0.36
    derived
    0.36
    Activations Density 0.000%

    No Known Activations