© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36289
    Prev
    Next
    INDEX
    Explanations

    from 2009 to 2017

    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_31_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
     Sah
    0.43
     صح
    0.43
     Creative
    0.40
     IL
    0.40
     Il
    0.40
     İç
    0.39
     çizg
    0.38
    }"]
    0.38
     Michigan
    0.37
     creative
    0.37
    POSITIVE LOGITS
    head
    0.41
    xn
    0.38
    耆
    0.38
    atibus
    0.38
    ipin
    0.37
    evident
    0.37
    xs
    0.36
    Head
    0.36
     SSm
    0.35
     दीजिए
    0.35
    Activations Density 0.002%

    No Known Activations