INDEX

Explanations

words related to bike repair

oai_token-act-pair · gemini-2.0-flash

technical documentation and hardware

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 funny

-1.48

funny

-1.18

 Funny

-1.06

Funny

-0.97

 drôle

-0.89

 engraçado

-0.79

 funniest

-0.79

 screw

-0.69

 Screw

-0.69

qrstuvwxyz

-0.65

POSITIVE LOGITS

 carriage

0.53

 AppBundle

0.49

NKC

0.49

AlterField

0.48

données

0.48

abestanden

0.47

 premiere

0.46

 counters

0.46

 counter

0.46

 UNIC

0.44

Activations Density 2.333%

words related to bike repair

technical documentation and hardware

No Comments

No Known Activations