INDEX

Explanations

technical terms related to the front and rear of vehicles and other objects

oai_token-act-pair · gemini-2.0-flash

front

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 front

-2.77

Front

-2.50

front

-2.42

 Front

-2.36

 FRONT

-2.27

FRONT

-2.16

 fronts

-1.88

fron

-1.63

 fron

-1.42

 Fron

-1.40

POSITIVE LOGITS

AxisAlignment

0.57

 Carra

0.56

landet

0.51

chre

0.48

ดิน

0.48

Nesta

0.47

 Übergang

0.46

guruan

0.46

 uncontrollable

0.46

SequentialGroup

0.46

Activations Density 5.260%

technical terms related to the front and rear of vehicles and other objects

front

No Comments

No Known Activations