© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13057
    Prev
    Next
    INDEX
    Explanations

    occurrences of first person pronouns plus an auxiliary verb, often, but not always, "can".

    oai_token-act-pair · gemini-2.0-flash

    tech forum discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ValueStyle
    -0.97
    aarrggbb
    -0.82
    MemoryWarning
    -0.81
     EconPapers
    -0.79
     Roskov
    -0.75
     فريبيس
    -0.73
    SequentialGroup
    -0.73
    PerformLayout
    -0.72
    MigrationBuilder
    -0.71
    setupUi
    -0.70
    POSITIVE LOGITS
     jail
    0.47
    })_{
    0.43
    zij
    0.42
    em
    0.41
     Sir
    0.39
    OneToMany
    0.39
    trans
    0.39
    bani
    0.38
     trans
    0.38
     Jail
    0.38
    Activations Density 3.718%

    No Known Activations