© 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. 14000
    Prev
    Next
    INDEX
    Explanations

    usages of "I", "would", "do" and "not" within a short distance of each other

    oai_token-act-pair · gemini-2.0-flash

    Expressing opinions/beliefs

    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
    +#+#
    -0.68
    BufferException
    -0.63
    WritableDatabase
    -0.59
    aarrggbb
    -0.57
    ificantly
    -0.57
    RegressionTest
    -0.55
     محفوظة
    -0.55
    bibfield
    -0.55
    utebol
    -0.54
    WithError
    -0.54
    POSITIVE LOGITS
     rule
    0.55
    complexContent
    0.51
    writeFieldEnd
    0.48
    Personendaten
    0.48
     Exacts
    0.46
     Eye
    0.46
    freude
    0.46
    AutoScaleMode
    0.46
    ManagedBean
    0.45
    viation
    0.45
    Activations Density 1.611%

    No Known Activations