© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 69355
    Prev
    Next
    INDEX
    Explanations

    say 'special characters'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    㑬
    0.36
    })$-
    0.35
    )").
    0.35
    }}:=\
    0.35
     व्हाट
    0.34
    ည့်
    0.34
    "]);
    0.34
    !"));
    0.33
    }"),
    0.33
    یں۔
    0.33
    POSITIVE LOGITS
    ēt
    0.39
    ഞ്ഞു
    0.38
    ů
    0.38
    Sent
    0.35
    ār
    0.35
    mere
    0.35
    —
    0.34
    ье
    0.34
    ní
    0.33
    มากขึ้น
    0.33
    Activations Density 0.478%

    No Known Activations