© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13182
    Prev
    Next
    INDEX
    Explanations

    the word "ability" alone or in combination with related adjectives or nouns

    oai_token-act-pair · gemini-2.0-flash

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     ability
    -2.22
     Ability
    -1.83
    Ability
    -1.77
    ability
    -1.51
     Fähigkeit
    -1.33
     abilities
    -1.27
     inability
    -1.23
     capability
    -1.18
     capacité
    -1.14
     kemampuan
    -1.10
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.89
    DotNetBar
    0.83
    MessageInfo
    0.67
    tvguidetime
    0.65
    aarrggbb
    0.65
    ConstraintMaker
    0.65
    RTEE
    0.65
    MigrationBuilder
    0.64
    клопе
    0.63
     cherchés
    0.62
    Activations Density 1.150%

    No Known Activations