INDEX

Explanations

words that indicate categories, activities, or organizations

oai_token-act-pair · gemini-2.0-flash

sport

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

culo

-0.49

kreis

-0.48

suc

-0.46

cules

-0.46

mulo

-0.45

ForValue

-0.45

ági

-0.42

kräf

-0.42

olé

-0.42

shou

-0.42

POSITIVE LOGITS

 defaultstate

0.88

tagHelperRunner

0.73

AnchorStyles

0.67

/*

0.66

 Económica

0.65

RTDA

0.64

 تضيفلها

0.62

complexContent

0.62

 kasarigan

0.61

DebuggerNonUser

0.61

Activations Density 1.566%

words that indicate categories, activities, or organizations

sport

No Comments

No Known Activations