© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6525
    Prev
    Next
    INDEX
    Explanations

    rising or falling

    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_39_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
     নিত
    0.41
    Bent
    0.40
    Respondent
    0.38
     Ming
    0.37
    Joy
    0.37
    Kor
    0.37
    Mid
    0.36
    焚
    0.36
    Mint
    0.36
    Upp
    0.35
    POSITIVE LOGITS
    ising
    0.47
     faster
    0.40
    AssetName
    0.40
     भगत
    0.38
    粦
    0.38
    ખો
    0.38
     accelerating
    0.37
    ിക്കുന്നത്
    0.37
     বৈঠকে
    0.37
    兴趣
    0.37
    Activations Density 0.074%

    No Known Activations