© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7649
    Prev
    Next
    INDEX
    Explanations

    words containing "flo", "ro", or "sim"

    oai_token-act-pair · gemini-2.0-flash

    technical and random language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.71
     uncin
    -0.57
     AssemblyCulture
    -0.57
    ziesz
    -0.56
    LookAnd
    -0.56
     brooms
    -0.55
    SourceChecksum
    -0.54
    Jegyzetek
    -0.53
    rB
    -0.53
     MediatR
    -0.52
    POSITIVE LOGITS
     onAnimation
    0.56
    Portale
    0.51
    sidemargin
    0.47
    ContextCompat
    0.45
    providedIn
    0.45
    — 
    0.44
    脚注の使い方
    0.44
    PageContext
    0.43
     SH
    0.43
    posedge
    0.43
    Activations Density 1.328%

    No Known Activations