© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260511
    Prev
    Next
    INDEX
    Explanations

    point that out

    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_22_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
    珽
    0.47
    ياب
    0.46
     Depot
    0.46
     হ্
    0.46
    一般
    0.44
    Theater
    0.43
    ഗം
    0.43
    ﺐ
    0.43
    वर्ल्ड
    0.42
    勰
    0.42
    POSITIVE LOGITS
     didn
    0.46
     altura
    0.45
     labelled
    0.43
    ர்த்து
    0.43
    áf
    0.41
     privately
    0.41
     X
    0.40
    ahi
    0.39
     psychic
    0.39
     removing
    0.39
    Activations Density 0.000%

    No Known Activations