© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40321
    Prev
    Next
    INDEX
    Explanations

    letter writing or explanations

    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_11_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
    𝙫
    0.43
    𝙩
    0.41
    correo
    0.41
    邮件
    0.40
    োলার
    0.39
    Postal
    0.39
    اريخ
    0.39
    ಕ್ಷಣ
    0.39
    큥
    0.39
    邮
    0.38
    POSITIVE LOGITS
     l
    0.44
    }
    0.42
    ]
    0.36
    !
    0.36
     soundtrack
    0.35
     textbook
    0.35
    )
    0.34
    ↵↵
    0.33
     cities
    0.33
     well
    0.33
    Activations Density 0.045%

    No Known Activations