© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194300
    Prev
    Next
    INDEX
    Explanations

    FL Studio, Ableton, Logic Pro, GarageBand

    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_4_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
    ।
    0.12
     y
    0.12
    ?
    0.11
     il
    0.11
    িয়া
    0.11
    ید
    0.11
    
    0.11
     d
    0.10
    ]
    0.10
    тый
    0.10
    POSITIVE LOGITS
    n
    0.19
    g
    0.18
    et
    0.16
    e
    0.16
    en
    0.15
    a
    0.15
    y
    0.15
    c
    0.15
    p
    0.15
    as
    0.15
    Activations Density 0.001%

    No Known Activations