INDEX

Explanations

code-related terms, especially related to Android.

oai_token-act-pair · gemini-2.0-flash

say "("

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 EconPapers

-1.30

 صوتيه

-1.29

EndGlobalSection

-1.21

GEBURTSDATUM

-1.21

 itſelf

-1.16

 дописавши

-1.13

 doInBackground

-1.11

tagHelperRunner

-1.11

 ―――――

-1.09

 ſche

-1.07

POSITIVE LOGITS

0.68

0.57

0.47

（

0.46

0.45

0.42

0.41

0.40

Po

0.40

as

0.40

Activations Density 1.524%

code-related terms, especially related to Android.

say "("

No Comments

No Known Activations