© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215772
    Prev
    Next
    INDEX
    Explanations

    "for" followed by meal or "the" followed by story title

    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_16_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
     octave
    0.48
    Proceedings
    0.47
    로
    0.47
    Freeze
    0.46
    楤
    0.46
    팔
    0.46
     ongeveer
    0.45
    ဤ
    0.45
     ਨ
    0.44
    ètent
    0.44
    POSITIVE LOGITS
     che
    0.43
     Bond
    0.41
     ecc
    0.41
     str
    0.41
     corre
    0.40
     ang
    0.40
    щик
    0.40
     uncle
    0.40
     Bar
    0.40
    敞
    0.39
    Activations Density 0.000%

    No Known Activations