© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111433
    Prev
    Next
    INDEX
    Explanations

    acronyms like rl, BS, urb

    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_2_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
     cortar
    1.06
    )،
    0.98
     ferramenta
    0.98
    IA
    0.97
     cognitiva
    0.96
    ە
    0.95
     prehr
    0.93
     justific
    0.92
    ോ
    0.92
    ار
    0.92
    POSITIVE LOGITS
    v
    1.33
    te
    1.20
    n
    1.18
    daki
    1.10
    ’
    1.09
     I
    1.05
     (
    1.00
    lt
    0.99
    지
    0.98
    וד
    0.97
    Activations Density 0.000%

    No Known Activations