© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97268
    Prev
    Next
    INDEX
    Explanations

    Ireland, sugar, protection

    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_14_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
     كأس
    0.56
     م
    0.52
     Iraqi
    0.51
     സുമിത്ര
    0.50
    USAGE
    0.49
     മ
    0.49
     н
    0.48
    ወ
    0.48
    need
    0.47
     ب
    0.46
    POSITIVE LOGITS
    ]
    0.57
    opl
    0.52
    from
    0.52
    iden
    0.52
    uo
    0.51
    pa
    0.51
    );
    0.50
    ]:
    0.49
    eri
    0.49
     cabins
    0.49
    Activations Density 0.009%

    No Known Activations