INDEX

Explanations

words related to internet communication systems

oai_token-act-pair · gemini-2.0-flash

group

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

Espèce

-0.61

⟬

-0.54

graphie

-0.53

reamble

-0.53

 Italijani

-0.52

 &___

-0.52

terase

-0.52

sbericht

-0.51

فایل‌لار

-0.51

leneck

-0.51

POSITIVE LOGITS

 group

0.89

 groups

0.81

 groupe

0.75

 gruppo

0.75

 grup

0.72

 grupo

0.69

group

0.69

 groupes

0.68

groups

0.64

Group

0.63

Activations Density 1.561%

words related to internet communication systems

group

No Comments

No Known Activations