© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20052
    Prev
    Next
    INDEX
    Explanations

    dosing frequency

    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_56_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
    apha
    0.40
    াউন্ড
    0.38
    ⵔ
    0.37
     पढ़ेंः
    0.35
     Wiesbaden
    0.35
    semb
    0.34
    ባቢ
    0.34
    avkh
    0.34
     συνα
    0.34
    viv
    0.33
    POSITIVE LOGITS
     q
    1.41
     BID
    1.27
     Q
    1.20
    BID
    1.18
     bid
    1.13
     TID
    1.10
     Bid
    1.09
    Bid
    1.09
     tid
    1.07
     QD
    1.03
    Activations Density 0.117%

    No Known Activations