© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17975
    Prev
    Next
    INDEX
    Explanations

    brochure

    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_15_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
     c
    0.64
     p
    0.58
     r
    0.54
     d
    0.54
     parcels
    0.52
     t
    0.52
     ph
    0.51
     P
    0.50
     hort
    0.49
     प्रारंभ
    0.48
    POSITIVE LOGITS
    𒀭
    0.56
    timeStamp
    0.55
     hashedPassword
    0.55
    Incidentally
    0.53
     marred
    0.52
    짖
    0.52
    දා
    0.51
     allError
    0.50
    ᴰ
    0.50
    waveform
    0.50
    Activations Density 0.001%

    No Known Activations