© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37668
    Prev
    Next
    INDEX
    Explanations

    LaTex, La Poste, La Fontaine, cannon

    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_3_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
    た
    0.90
    tr
    0.89
    t
    0.85
    ts
    0.84
    Sight
    0.80
    ttes
    0.79
    ten
    0.78
    0
    0.77
    ty
    0.75
    ti
    0.75
    POSITIVE LOGITS
    ی
    0.99
    ים
    0.83
    ों
    0.77
    ের
    0.73
    ]
    0.71
    ો
    0.71
    یتی
    0.71
    یە
    0.68
    )
    0.67
     proponent
    0.66
    Activations Density 0.000%

    No Known Activations