© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14915
    Prev
    Next
    INDEX
    Explanations

    various forms of the words "achieve" and "attain"

    oai_token-act-pair · gemini-2.0-flash

    achieve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     SwiftUI
    -0.60
    enumii
    -0.56
    antMatchers
    -0.51
    ้อมูล
    -0.49
    AccessorTable
    -0.48
    latego
    -0.47
    PrototypeOf
    -0.47
    GEBURTSDATUM
    -0.47
    انجليز
    -0.47
    LabelTagHelper
    -0.46
    POSITIVE LOGITS
    veaux
    0.66
    iteritems
    0.59
    Reached
    0.59
     onAnimation
    0.56
     bakso
    0.53
    ANTI
    0.53
    encodeWith
    0.53
     Tér
    0.53
    AxisAlignment
    0.52
    anabe
    0.52
    Activations Density 1.041%

    No Known Activations