INDEX

Explanations

words related to children, medicine, and cognitive skills

oai_token-act-pair · gemini-2.0-flash

gibberish

np_token-act-pair-logits · gemini-2.0-flash

foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ThemeData

-0.53

 emperador

-0.47

titure

-0.47

ələ

-0.47

 jsPsych

-0.46

emus

-0.45

 psycho

-0.45

 maî

-0.45

cdk

-0.44

ึ่ง

-0.44

POSITIVE LOGITS

 مشين

0.90

 resourceCulture

0.80

StoryboardSegue

0.76

Hochspringen

0.64

 OkHttpClient

0.61

apimachinery

0.59

bcryptjs

0.57

 lenker

0.56

TagHelpers

0.55

impulan

0.54

Activations Density 1.781%

words related to children, medicine, and cognitive skills

gibberish

foreign words

No Comments

No Known Activations