INDEX

Explanations

scientific terms about biofuels and related funding

oai_token-act-pair · gemini-2.0-flash

Power and energy

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 protoimpl

-0.58

CloseOperation

-0.57

ẵng

-0.57

 ✭✭

-0.52

("")]

-0.49

 mergeFrom

-0.49

 pluie

-0.49

Filmographie

-0.48

 createStore

-0.48

scribers

-0.47

POSITIVE LOGITS

 power

0.93

power

0.84

bio

0.76

 powered

0.76

POWER

0.75

 POWER

0.74

 Power

0.74

 énergé

0.71

 energy

0.71

Power

0.69

Activations Density 2.943%

scientific terms about biofuels and related funding

Power and energy

No Comments

No Known Activations