© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14525
    Prev
    Next
    INDEX
    Explanations

    indicators of negative feelings, problems, and how to reverse them

    oai_token-act-pair · gemini-2.0-flash

    words related to moral dilemmas

    np_token-act-pair-logits · gpt-4o-mini

    snippets of text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     itſelf
    -1.02
     myſelf
    -0.93
    aarrggbb
    -0.90
     ſtate
    -0.90
     فريبيس
    -0.88
     purpoſe
    -0.86
     feroit
    -0.84
     ſche
    -0.82
     Efq
    -0.80
     Monfieur
    -0.79
    POSITIVE LOGITS
     consenti
    0.44
    FieldDescriptor
    0.43
    up
    0.42
    LANDS
    0.40
     who
    0.39
     confor
    0.39
     mati
    0.39
     pró
    0.39
     n
    0.39
    ICATION
    0.38
    Activations Density 9.729%

    No Known Activations