© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4612
    Prev
    Next
    INDEX
    Explanations

    words related to portals and other dimensions in fantasy stories, possibly including power inverters

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Kaiser
    -0.44
    Tach
    -0.44
     done
    -0.41
    trico
    -0.41
     finally
    -0.40
     prima
    -0.38
    gov
    -0.38
    لط
    -0.38
     cost
    -0.37
    text
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.98
     насељу
    0.95
     שוליים
    0.92
     tartalomajánló
    0.91
    istoitu
    0.89
    তথ্যসূত্র
    0.83
    IntoConstraints
    0.82
    MigrationBuilder
    0.78
    Rptr
    0.77
     виправивши
    0.75
    Activations Density 1.431%

    No Known Activations