© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7953
    Prev
    Next
    INDEX
    Explanations

    json dumps, fromJson, compare

    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_40_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
     extrapolate
    0.42
    Merging
    0.41
    }()
    0.40
    Merged
    0.38
     estrict
    0.38
     merging
    0.38
     گری
    0.38
     tubular
    0.38
    romycin
    0.38
     processed
    0.37
    POSITIVE LOGITS
     JSONObject
    0.45
    toJson
    0.42
    JSONObject
    0.42
     Phoenix
    0.37
    到时候
    0.37
    到
    0.37
     CodeableConcept
    0.36
     gamb
    0.36
     [+
    0.36
     Joel
    0.36
    Activations Density 0.001%

    No Known Activations