© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198811
    Prev
    Next
    INDEX
    Explanations

    literary works

    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_50_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
    toFloat
    0.40
     Asia
    0.39
     cob
    0.38
     Dunne
    0.38
     Lesley
    0.38
     haj
    0.37
    𝕝
    0.37
     las
    0.36
    㭋
    0.36
     Cob
    0.35
    POSITIVE LOGITS
    Given
    0.43
     given
    0.43
    ㄣ
    0.43
    given
    0.40
     imposed
    0.40
    impose
    0.38
     consultants
    0.38
     exd
    0.37
    Joseph
    0.37
    precise
    0.37
    Activations Density 0.005%

    No Known Activations