INDEX

Explanations

the prefix "dis"

oai_token-act-pair · gemini-2.0-flash

dis

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

kuuta

-0.40

первых

-0.39

влению

-0.38

uttavia

-0.38

 Réponses

-0.38

erai

-0.36

 собі

-0.36

лео

-0.36

←

-0.34

"},

-0.34

POSITIVE LOGITS

 nahilalakip

0.61

contentLoaded

0.59

Portály

0.58

claimers

0.57

httphttps

0.57

inheritance

0.56

wikidata

0.56

Jäh

0.55

 BrowserModule

0.54

WebServlet

0.54

Activations Density 5.641%

the prefix "dis"

dis

No Comments

No Known Activations