© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207626
    Prev
    Next
    INDEX
    Explanations

    spread spectrum modulation

    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_19_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
    ab
    0.42
     כת
    0.41
    uksi
    0.40
     бу
    0.40
     м
    0.40
     أكبر
    0.40
    সাম
    0.39
     ח
    0.39
     וב
    0.38
    forceable
    0.38
    POSITIVE LOGITS
    Vic
    0.42
    Vet
    0.40
    νας
    0.39
     Vim
    0.38
    য়র
    0.38
    …</
    0.38
    引擎
    0.37
    敷
    0.37
    VAN
    0.36
     Petri
    0.36
    Activations Density 0.000%

    No Known Activations