© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131071
    Prev
    Next
    INDEX
    Explanations

    constantly

    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
     givenChar
    0.40
     returnPacket
    0.37
     inmediata
    0.36
    keits
    0.36
     điển
    0.35
    엌
    0.35
     immédi
    0.34
    밖에
    0.34
    下手
    0.34
    앜
    0.34
    POSITIVE LOGITS
     const
    2.84
    const
    2.73
     Const
    2.45
    Const
    2.41
     konst
    1.99
    CONST
    1.75
     constable
    1.73
     consta
    1.68
     Constable
    1.67
     constriction
    1.66
    Activations Density 0.035%

    No Known Activations