© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12152
    Prev
    Next
    INDEX
    Explanations

    the word "prior," some percentages, the word "explicit", and the word "retrospective"

    oai_token-act-pair · gemini-2.0-flash

    prior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     previous
    -0.88
    previous
    -0.84
    oa̍t
    -0.80
     précédents
    -0.74
     fédé
    -0.74
    StructEnd
    -0.70
     precedenti
    -0.69
     предыду
    -0.69
     $\$
    -0.68
    ModelSerializer
    -0.67
    POSITIVE LOGITS
    etCode
    0.62
    algo
    0.59
    </tr>
    0.54
    iography
    0.54
    KeySpec
    0.52
     The
    0.50
     somehow
    0.49
     decipher
    0.49
    RetentionPolicy
    0.49
    IEF
    0.47
    Activations Density 1.219%

    No Known Activations