© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1950
    Prev
    Next
    INDEX
    Explanations

    phrases in Croatian related to Facebook, SMS messages and data usage

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     kasarigan
    -0.65
    出版年
    -0.53
    Билгалдахарш
    -0.52
    verifyException
    -0.49
     المعيارى
    -0.49
    printStackTrace
    -0.48
    UserScript
    -0.48
    reza
    -0.47
    Portale
    -0.46
    setFlags
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.67
     suivants
    0.59
     coû
    0.54
     avoient
    0.53
     aveug
    0.52
     hâte
    0.52
     convertView
    0.52
     habet
    0.52
     découver
    0.52
     semblables
    0.51
    Activations Density 1.777%

    No Known Activations