INDEX

Explanations

words related to diversity and variability, especially in the context of statistics and scientific studies.

oai_token-act-pair · gemini-2.0-flash

extremely, highly

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__':

-1.00

__':

-0.76

__":

-0.74

ItemBackground

-0.69

 }}"></

-0.68

Efq

-0.68

참고

-0.67

tvguidetime

-0.66

請繼續往下閱讀

-0.62

 themſelves

-0.61

POSITIVE LOGITS

highly

0.60

 highly

0.59

Highly

0.58

 Highly

0.56

 extremely

0.56

extremely

0.53

 Extremely

0.52

webElementXpaths

0.52

 incredibly

0.51

 extrêmement

0.48

Activations Density 1.546%

words related to diversity and variability, especially in the context of statistics and scientific studies.

extremely, highly

No Comments

No Known Activations