INDEX

Explanations

words and names associated with legal or official proceedings and documents

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 himself

-0.73

himself

-0.72

حياته

-0.71

وفاته

-0.63

تقاوى

-0.61

idency

-0.61

 masculinity

-0.60

‍♂️

-0.59

 derselbe

-0.58

 ReSharper

-0.57

POSITIVE LOGITS

 herself

0.86

herself

0.61

she

0.60

AccessorTable

0.56

 Taktlose

0.54

CloseOperation

0.53

 powinna

0.51

 designs

0.51

 Kaur

0.50

synaptic

0.50

Activations Density 14.994%

words and names associated with legal or official proceedings and documents

No Comments

No Known Activations