INDEX

Explanations

instances of learning and growth.

oai_token-act-pair · gemini-2.0-flash

learning

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Tikang

-0.93

 InputDecoration

-0.92

^(@)

-0.80

ⓘ

-0.77

 purpoſe

-0.75

Билгалдахарш

-0.74

 GoogleFonts

-0.71

WritableDatabase

-0.71

SharedCtor

-0.67

 propOrder

-0.67

POSITIVE LOGITS

bindingNavigator

0.41

Lab

0.41

ngdoc

0.40

had

0.39

üksek

0.38

na

0.37

StringCopy

0.36

!"

0.36

 sparked

0.36

 rough

0.35

Activations Density 30.380%

instances of learning and growth.

learning

No Comments

No Known Activations