© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233831
    Prev
    Next
    INDEX
    Explanations

    ways to do something

    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_32_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
     Mock
    0.37
     e
    0.37
     ذریعے
    0.37
     Shit
    0.37
    祝い
    0.37
    可以通过
    0.37
    }°
    0.37
     तोह
    0.36
     proposal
    0.36
    கூ
    0.36
    POSITIVE LOGITS
    𝗋
    0.38
     spends
    0.37
     spent
    0.35
    ментів
    0.35
     சிறிது
    0.34
    ld
    0.34
     आंबेडकर
    0.33
    ‌ల
    0.33
    िक्की
    0.33
    మ్ము
    0.33
    Activations Density 0.006%

    No Known Activations