© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44665
    Prev
    Next
    INDEX
    Explanations

    charade

    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_3_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
     enlightened
    0.83
     sharpened
    0.71
     to
    0.65
     informed
    0.64
     at
    0.63
     as
    0.59
    𝑡
    0.59
     emerge
    0.58
     allotted
    0.58
     waveform
    0.58
    POSITIVE LOGITS
    2
    0.80
    7
    0.75
    人
    0.68
    ー
    0.68
    。
    0.65
    user
    0.64
    Mak
    0.64
    BBC
    0.64
    question
    0.63
    Exists
    0.63
    Activations Density 0.002%

    No Known Activations