© 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. 49245
    Prev
    Next
    INDEX
    Explanations

    Orca or Killer Whale

    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
     زبان
    0.40
    緻
    0.38
     ঘুরে
    0.38
     retreating
    0.37
    컨
    0.37
     Conch
    0.36
    csproj
    0.36
     CSI
    0.36
    jmp
    0.35
     jezik
    0.35
    POSITIVE LOGITS
    Tidak
    0.36
     πό
    0.35
    ಂತ
    0.34
    Таким
    0.34
    PLICATION
    0.34
     นํา
    0.34
    Nigeria
    0.34
    💹
    0.33
    PBS
    0.33
    ិត្ត
    0.33
    Activations Density 0.014%

    No Known Activations