© 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. 170642
    Prev
    Next
    INDEX
    Explanations

    It

    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
     proves
    0.53
    Worked
    0.45
     Worked
    0.44
    证明
    0.43
    worked
    0.40
     د
    0.39
     worked
    0.38
    ऑ
    0.37
     d
    0.37
     proving
    0.36
    POSITIVE LOGITS
     lead
    0.50
    Lead
    0.47
    lead
    0.46
     led
    0.45
     seraient
    0.44
     Lead
    0.44
     Led
    0.42
     werden
    0.42
    Led
    0.41
     leaves
    0.41
    Activations Density 0.004%

    No Known Activations