© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216525
    Prev
    Next
    INDEX
    Explanations

    say "bend"

    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_47_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
     bending
    1.85
     bend
    1.74
     bends
    1.74
    弯
    1.70
     folded
    1.65
     folding
    1.64
     fold
    1.60
    折
    1.59
     bent
    1.59
    彎
    1.58
    POSITIVE LOGITS
     Rocco
    0.40
    addSprite
    0.39
    scdn
    0.38
     महोत्सव
    0.37
     Neuro
    0.37
     Paco
    0.35
     coalition
    0.35
     Spawn
    0.34
     गोल्डन
    0.34
    फॉ
    0.34
    Activations Density 0.002%

    No Known Activations