© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10903
    Prev
    Next
    INDEX
    Explanations

    common words and phrases involved in giving an explanation or justification

    oai_token-act-pair · gemini-2.0-flash

    Legal/Formal arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    JsonProperty
    -0.53
    igu
    -0.48
    AYSIA
    -0.41
    CROSSTALK
    -0.40
     ↑
    -0.40
    가
    -0.40
     mecanismo
    -0.39
    仗
    -0.39
    UELA
    -0.39
    </em>
    -0.39
    POSITIVE LOGITS
     صوتيه
    0.84
     المعيارى
    0.82
     resourceCulture
    0.72
     незавершена
    0.72
     Wikimedijinoj
    0.70
    elemField
    0.68
    Personensuche
    0.67
    Osc
    0.66
    Datuak
    0.66
    MessageOf
    0.65
    Activations Density 1.320%

    No Known Activations