© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32303
    Prev
    Next
    INDEX
    Explanations

    code syntax and libraries

    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
    asty
    0.34
     সবচেয়ে
    0.33
     لله
    0.33
    假設
    0.33
    icide
    0.33
    早い
    0.33
    tiden
    0.33
    矚
    0.33
    錡
    0.33
    goed
    0.32
    POSITIVE LOGITS
    PCF
    0.48
    IntegerField
    0.45
    <0xA3>
    0.41
     whiff
    0.41
     MDF
    0.41
    matory
    0.40
    पीएफ
    0.39
     PSF
    0.39
     rjf
    0.39
     হাফ
    0.39
    Activations Density 0.051%

    No Known Activations