INDEX

Explanations

greetings in different languages, general conversational phrases and reactions to situations.

oai_token-act-pair · gemini-2.0-flash

Good and bad sentiment

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Geplaatst

-0.80

endregion

-0.76

 houſe

-0.74

########.

-0.73

 myſelf

-0.71

 {}));

-0.71

 Houſe

-0.68

 Hift

-0.66

 kasarigan

-0.65

**/

-0.65

POSITIVE LOGITS

 good

1.13

 Good

1.08

Good

1.05

good

1.04

 GOOD

0.98

GOOD

0.89

bad

0.82

 buenas

0.81

 mood

0.76

bad

0.72

Activations Density 0.596%

greetings in different languages, general conversational phrases and reactions to situations.

Good and bad sentiment

No Comments

No Known Activations