© 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. 48938
    Prev
    Next
    INDEX
    Explanations

    from the perspective

    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
     Afr
    0.36
     깨
    0.35
     yav
    0.35
     Properly
    0.33
     arro
    0.32
    算出
    0.32
    流入
    0.32
     почув
    0.32
     উদ্ভি
    0.32
     według
    0.32
    POSITIVE LOGITS
     backdrop
    0.38
    )}$.
    0.38
    isRequired
    0.37
    养
    0.37
    }$.
    0.36
    überküloz
    0.36
    diamond
    0.35
    jillo
    0.35
    的人
    0.34
    మంలో
    0.34
    Activations Density 0.007%

    No Known Activations