© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50432
    Prev
    Next
    INDEX
    Explanations

    assume positive intent

    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_30_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
     ቁ
    0.39
     TBR
    0.38
    ቓ
    0.36
     continuum
    0.36
    ikin
    0.35
    kart
    0.34
     taboo
    0.34
     efficacy
    0.34
     aise
    0.34
    섭
    0.34
    POSITIVE LOGITS
     hopeful
    0.45
     Hoffnung
    0.44
    आशा
    0.43
     optimistic
    0.42
     optimist
    0.39
     constructively
    0.39
    希望
    0.38
     можливо
    0.38
     Hope
    0.38
    Hope
    0.38
    Activations Density 0.046%

    No Known Activations