© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207207
    Prev
    Next
    INDEX
    Explanations

    diaeresis marks

    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_56_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
    iciais
    0.43
    acyj
    0.43
    (`#
    0.41
     बजकर
    0.40
    CCOCC
    0.39
    ++++++++++++++++
    0.39
    तौर
    0.39
    ktions
    0.38
     #-
    0.38
    ][$
    0.37
    POSITIVE LOGITS
    ï
    1.00
     ï
    0.94
     Ï
    0.88
    Ï
    0.87
    ĩ
    0.72
    ̈
    0.71
     ї
    0.63
    ¨
    0.63
    ӥ
    0.61
    ī
    0.60
    Activations Density 0.000%

    No Known Activations