INDEX

Explanations

words related to modifications, crafting, and hobbies

oai_token-act-pair · gemini-2.0-flash

Material types

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

modelBuilder

-0.68

 disponibilités

-0.60

SuppressMessage

-0.55

 defaultstate

-0.53

 veze

-0.52

//

-0.49

 camada

-0.48

 défend

-0.47

 arrivant

-0.47

 venons

-0.47

POSITIVE LOGITS

texttt

0.61

 plastic

0.60

 brass

0.59

tvguidetime

0.58

 cardboard

0.56

 Kart

0.55

 kart

0.55

 denim

0.54

Kart

0.52

 Card

0.51

Activations Density 3.555%

words related to modifications, crafting, and hobbies

Material types

No Comments

No Known Activations