© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5557
    Prev
    Next
    INDEX
    Explanations

    statements about a location

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    QtCore
    -0.55
    PutMapping
    -0.48
    mest
    -0.45
    oor
    -0.43
     macam
    -0.43
     ecco
    -0.43
    +#+#
    -0.43
     blessé
    -0.43
    orei
    -0.43
     معرفی
    -0.42
    POSITIVE LOGITS
    UnusedPrivate
    0.81
    RegressionTest
    0.72
     BoxFit
    0.68
    IndentedString
    0.63
    estacks
    0.63
     Normdatei
    0.60
     defaultstate
    0.60
    ukunft
    0.60
    TagHelpers
    0.59
    xFFFFFF
    0.59
    Activations Density 0.764%

    No Known Activations