© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139609
    Prev
    Next
    INDEX
    Explanations

    This neuron describes types or modes of signal generators

    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_12_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
    Bonjour
    0.54
     U
    0.48
     Baw
    0.46
     I
    0.45
    guru
    0.45
    Is
    0.45
    Hallo
    0.44
    Rather
    0.44
    Hmm
    0.44
    î
    0.44
    POSITIVE LOGITS
     поколения
    0.58
     Casinos
    0.53
     casinos
    0.52
     ہزار
    0.51
     возмо
    0.51
    łuż
    0.51
    ного
    0.50
    ustible
    0.50
    alysis
    0.49
    ㄑ
    0.49
    Activations Density 0.000%

    No Known Activations