© 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. 11466
    Prev
    Next
    INDEX
    Explanations

    the greetings of "Hi" or "Hello" followed sometimes by other words.

    oai_token-act-pair · gemini-2.0-flash

    Hi

    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
     desired
    -0.72
    Jim
    -0.71
     Jim
    -0.68
    Hi
    -0.65
    ToAction
    -0.65
    riwal
    -0.65
     EdgeInsets
    -0.64
    adaptiveStyles
    -0.60
     desirable
    -0.60
    apimachinery
    -0.58
    POSITIVE LOGITS
    хьтан
    0.58
    égard
    0.58
     crédit
    0.58
    rupulous
    0.57
     tartalomajánló
    0.55
    ","+
    0.54
    "]/
    0.54
    hésitez
    0.53
    UNTAIN
    0.53
     Gj
    0.53
    Activations Density 0.756%

    No Known Activations