© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11532
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to beaches and the coast

    oai_token-act-pair · gemini-2.0-flash

    beaches and shorelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RUnlock
    -0.76
     Мексичка
    -0.71
    VersionUID
    -0.71
    MigrationBuilder
    -0.66
    ApiModelProperty
    -0.66
    principalTable
    -0.66
     FetchType
    -0.64
     onPostExecute
    -0.64
    RTEX
    -0.62
    oa̍t
    -0.61
    POSITIVE LOGITS
    rawDesc
    0.45
     single
    0.43
     solo
    0.43
     anteriormente
    0.41
     op
    0.40
     επι
    0.40
    nosis
    0.40
    odis
    0.40
    opp
    0.40
    єра
    0.40
    Activations Density 1.386%

    No Known Activations