INDEX

Explanations

text related to fuel consumption in cars

oai_token-act-pair · gemini-2.0-flash

fuel

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 fuel

-2.48

 Fuel

-2.47

Fuel

-2.38

fuel

-2.23

 FUEL

-2.20

FUEL

-2.11

 fuels

-1.97

 Fuels

-1.78

燃料

-1.60

fuels

-1.60

POSITIVE LOGITS

 NSCoder

0.61

PerformLayout

0.50

 Robo

0.48

oneofs

0.46

 Argyle

0.46

LError

0.46

躇

0.46

pergillus

0.45

uchtigkeit

0.45

bia

0.44

Activations Density 1.522%

text related to fuel consumption in cars

fuel

No Comments

No Known Activations