© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87927
    Prev
    Next
    INDEX
    Explanations

    controller detection

    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_23_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
     earnestly
    0.42
    ങ്ങള്‍ക്ക്
    0.40
    🚒
    0.40
    ibaldi
    0.40
     напом
    0.39
    ಶ್ಯ
    0.38
     RATES
    0.38
     እስከ
    0.38
     ['(?
    0.38
    ﾀ
    0.37
    POSITIVE LOGITS
    i
    0.45
    atsioon
    0.44
     कैबिनेट
    0.44
     Ere
    0.44
     slim
    0.43
     French
    0.42
     Ancient
    0.42
    ાઈ
    0.41
     reactions
    0.41
    esper
    0.41
    Activations Density 0.000%

    No Known Activations