© 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. 75140
    Prev
    Next
    INDEX
    Explanations

    some, others, more, less

    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
    첨
    0.41
     첨
    0.38
     expectation
    0.37
    Addition
    0.37
     attachment
    0.36
     ricevere
    0.35
     bemo
    0.34
    𝜃
    0.34
     termos
    0.34
     अटेम्प्ट
    0.34
    POSITIVE LOGITS
    雳
    0.41
     pliers
    0.39
    敵人
    0.38
     Dla
    0.38
     ///
    0.37
     révolution
    0.37
    UOUS
    0.37
    skiej
    0.36
    ressen
    0.36
    ത്തിന
    0.35
    Activations Density 0.004%

    No Known Activations