INDEX

Explanations

physical dimensions and objects related to buildings, clothing, or instruments

oai_token-act-pair · gemini-2.0-flash

words related to size or shape

np_token-act-pair-logits · gemini-2.0-flash

dimension

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

anyahu

-0.60

OGND

-0.58

styleType

-0.57

 AssemblyCompany

-0.56

 TextAppearance

-0.54

ecore

-0.53

 technics

-0.53

SequentialGroup

-0.52

 ModelExpression

-0.50

 Yarm

-0.50

POSITIVE LOGITS

BASEPATH

0.63

EndProject

0.57

ptid

0.54

 resourceCulture

0.51

posedge

0.50

routeProvider

0.49

lsch

0.48

 belangrij

0.48

vide

0.47

standing

0.47

Activations Density 3.434%

physical dimensions and objects related to buildings, clothing, or instruments

words related to size or shape

dimension

No Comments

No Known Activations