INDEX

Explanations

pronouns, conjunctions, and punctuation

oai_token-act-pair · gemini-2.0-flash

foreign language text (possibly code)

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

end of sentence

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

Архівовано

-0.63

awaiter

-0.52

 defaultstate

-0.52

 Collo

-0.51

 OMITTED

-0.51

urator

-0.50

 doInBackground

-0.50

êche

-0.50

 EdgeInsets

-0.50

inco

-0.49

POSITIVE LOGITS

 referenties

0.66

 AssemblyProduct

0.62

 naturlig

0.58

出版年

0.55

Naturally

0.54

 Naturally

0.53

ALIAN

0.52

 trattano

0.51

ftagPool

0.50

 الرياضيه

0.50

Activations Density 5.401%

pronouns, conjunctions, and punctuation

foreign language text (possibly code)

end of sentence

No Comments

No Known Activations