© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202952
    Prev
    Next
    INDEX
    Explanations

    audio, PulseAudio, ALSA, ports

    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_37_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
    茥
    0.37
     جام
    0.37
     stains
    0.36
    active
    0.36
     ఉప
    0.36
    ல்லாம்
    0.36
    etur
    0.35
     margins
    0.35
    堃
    0.35
    ocytic
    0.35
    POSITIVE LOGITS
    Hilbert
    0.51
     Hilbert
    0.49
     Hil
    0.47
    Hil
    0.46
     hil
    0.44
    Albert
    0.44
     Saka
    0.41
     sonidos
    0.40
    ドリ
    0.40
     traslado
    0.39
    Activations Density 0.002%

    No Known Activations