INDEX

Explanations

the word "modern" and related concepts

oai_token-act-pair · gemini-2.0-flash

modern

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

 Kini

-0.58

 vieille

-0.54

OfType

-0.52

strcat

-0.51

RegressionTest

-0.50

^(@)

-0.49

esterday

-0.49

powerful

-0.48

Gov

-0.48

 Tentang

-0.47

POSITIVE LOGITS

ReusableCell

0.73

mtrl

0.60

ModelAdmin

0.58

Чыганаклар

0.53

 doInBackground

0.50

úgó

0.49

 oprot

0.49

NgModule

0.49

typeorm

0.47

InjectAttribute

0.47

Activations Density 4.318%

the word "modern" and related concepts

modern

No Comments

No Known Activations