© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    prefixes with "over-"

    oai_token-act-pair · gemini-2.0-flash

    over

    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
     rospy
    -0.57
    횟
    -0.57
    IntoConstraints
    -0.54
    ETCH
    -0.53
    QUADS
    -0.52
    typeorm
    -0.52
    ganu
    -0.51
    NavigationView
    -0.51
    期刊论文
    -0.50
    agrid
    -0.50
    POSITIVE LOGITS
    rrggbb
    0.60
    BeginContext
    0.57
    Hauptartikel
    0.53
    لكتر
    0.51
     démocr
    0.51
    MigrationBuilder
    0.50
     propOrder
    0.47
    esac
    0.45
    findpost
    0.45
     enfans
    0.45
    Activations Density 1.816%

    No Known Activations