© 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. 10853
    Prev
    Next
    INDEX
    Explanations

    the suffix "ini" and the word "impression"

    oai_token-act-pair · gemini-2.0-flash

    ini

    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
    ini
    -2.92
    INI
    -2.41
     ini
    -1.49
    inii
    -1.41
    inis
    -1.40
    Ini
    -1.39
     INI
    -1.30
     Ini
    -1.02
    inin
    -0.98
    ino
    -0.88
    POSITIVE LOGITS
     betweenstory
    0.78
     Superhosts
    0.74
    ftagPool
    0.70
    +#+
    0.69
    verifyException
    0.68
    enumii
    0.68
    Hochspringen
    0.68
    évaluateur
    0.67
     '\\;'
    0.67
    $_['
    0.67
    Activations Density 1.165%

    No Known Activations