© 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. 3512
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with child psychology and parental relationships, especially those concerning attachment and potential disorders.

    oai_token-act-pair · gemini-2.0-flash

    attachment

    np_max-act · 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
     فريبيس
    -0.81
     myſelf
    -0.70
    enumii
    -0.69
    enumi
    -0.68
    LEncoder
    -0.65
     NUKAT
    -0.64
    terase
    -0.63
    Rüyada
    -0.61
    aarrggbb
    -0.61
    IsMutable
    -0.61
    POSITIVE LOGITS
    #+#
    0.57
     loving
    0.50
    gdx
    0.47
    assertIn
    0.45
     affectionate
    0.45
    ubility
    0.45
    affection
    0.44
     peluche
    0.43
    └──
    0.43
    CONSIN
    0.43
    Activations Density 0.748%

    No Known Activations